Agentic RAG: making retrieval a decision the agent controls
Short answer Agentic RAG is retrieval-augmented generation where the agent decides when to retrieve,...
#Agents
5343 articles tagged with Agents
Four confirmed cases show agentic AI models weaponizing their own recovery capabilities for persistence. The same featur...
Four confirmed cases show agentic AI models weaponizing their own recovery capabilities for persistence. The same feature that aids defense becomes the attack vector. #AI #Cybersec...
Writer says its new Palmyra X6 model cuts AI agent costs by 52% as token spending surges
Writer , the enterprise AI agent platform used by Fortune 500 companies including Accenture, Uber, and Vanguard, released its new flagship model Palmyra X6 today, alongside a rebui...
タムズにもAnthropicがあったらよかったですねAgentic reliability and evaluations : Enterprises that got burned by a bad eval are the most l...
タムズにもAnthropicがあったらよかったですねAgentic reliability and evaluations : Enterprises that got burned by a bad eval are the most likely to remove humans from the loop, not the least https://...
Agentic Engineering Is Just Everything We Haven't Been DoingArticle URL: https://blog.matthewbrunelle.com/agentic-engine...
Agentic Engineering Is Just Everything We Haven't Been DoingArticle URL: https://blog.matthewbrunelle.com/agentic-engineering-is-just-everything-we-havent-been-doing/ Comments URL:...
Celona launches Orion agentic wireless platform built for physical AI and robotics. Celona launches Orion, a unified age...
Celona launches Orion agentic wireless platform built for physical AI and robotics. Celona launches Orion, a unified agentic wireless platform merging private 5G, Wi-Fi, cellular, ...
Cactus Needle 2 LLM for Tiny Devices: an 14MB Agentic LLM for phones, wearables, smart home and robots ; the whole model...
Cactus Needle 2 LLM for Tiny Devices: an 14MB Agentic LLM for phones, wearables, smart home and robots ; the whole model is a single 14MB binary that runs in 28MB of RAM #LLM #AI h...
An AI agent read 13 invoices and blocked $1,411.25 in bad payments
I handed an AI agent 13 invoices and a list of what we had actually ordered. It approved 10 of them,...
Why your AI agent instruction files drift across machines
You write CLAUDE.md once. Six months later there are eighteen of them on your laptop and you cannot...
Scaling AI agents with trustworthy dataBusiness and technology leaders need no convincing that the time of agentic AI is...
Scaling AI agents with trustworthy dataBusiness and technology leaders need no convincing that the time of agentic AI is here. Organizations are rapidly adopting agents, and few ex...
Building a Production AI Agent in Spring Boot: The Append-Only Audit Trail (Part 13)
The security page of an AI meeting recorder with over two million users is a trophy case. SOC2...
Not that complicated: A firm deploying an AI agent and it causes harm to someone else, the firm is responsible for that ...
Not that complicated: A firm deploying an AI agent and it causes harm to someone else, the firm is responsible for that harm. #AIAI agents aren’t legally respo...
Efficient Reinforcement Learning for Long-Horizon Tool-Use Agentic Tasks. New RL system SINKFLEX-RL cuts VRAM 19.7% for ...
Efficient Reinforcement Learning for Long-Horizon Tool-Use Agentic Tasks. New RL system SINKFLEX-RL cuts VRAM 19.7% for long-horizon agent tasks, boosting Tau2Bench retail rewards ...
Error Messages as an Agent Interface: Designing API Failures an Agent Can Recover FromAn AI agent only sees what your er...
Error Messages as an Agent Interface: Designing API Failures an Agent Can Recover FromAn AI agent only sees what your error body contains. A field-by-field guide to API errors agen...
Agentic claims in iGaming, mapped—and a test for telling them apart
Fourin 5 iGaming companies use AI, but only 1 in 5 sees meaningful ROI. This gap has led to a flood of "agentic" claims from CRM suites to full platforms. The post Agentic claims i...
U.S. HEALTH SYSTEMS EMBRACE AGENTIC AI AS STEER HEALTH DEPLOYS END TO END CLINICAL ENGINE ACROSS NATIONWIDE HEALTHCARE ENTERPRISES
DALLAS, TX (August 12, 2026): Steer Health, the pioneer in enterprise-grade agentic artificial intelligence for healthcare, today announced the widespread, multi-facility adoption ...
Agentic Profiles Could Strengthen AI Governance
Artificial intelligence is moving rapidly from systems that answer questions to agents that can pursue objectives, make decisions and act across digital
SpaceXAI Launches Grok 4.6 With Focus On Agentic AI: Here's What's New & Who Gets It
SpaceXAI has launched Grok 4.6, its new flagship AI model designed for long-running agentic tasks, coding, research and visual work. The model is available through Cursor, Grok Bui...
Building a Production AI Agent in Spring Boot: Tenant Isolation (Part 12)
An AI meeting recorder with over two million users stored every meeting on the platform in one...
The Agentic Economy Needs a Market for Work
AI agents will need open markets where they can find tasks, hire help, prove results, and receive payment.
Building a Fair Benchmark for AI Agent Memory Systems
Everyone is building AI memory systems. But how do we know which ones actually work? As AI agents...
Building Your First AI Agent from Scratch (No Framework)
How to build a production-shaped agent in ~150 lines of Python — no LangChain, no CrewAI, nothing you...
DeepSeek updates V4 Pro model, eyes AI agent development
DeepSeek updated its flagship V4 Pro model with enhanced performance late on Wednesday, while it eyes developing artificial intelligence agents that can compete with services like ...
FlowScout generates tool-integrated agentic workflows from historical records, improving tool invocation correctness by ...
FlowScout generates tool-integrated agentic workflows from historical records, improving tool invocation correctness by 92.69% and execution quality by 17.66% over baselines like R...